big_data_casestudies_2.ppt

1
Ilkay ALTINTAS and Geoffrey FOX - March, 2014
Big Data Use Cases and Requirements

2
Requirements and Use Case Subgroup
2
The focus is to form a community of interest from industry, academia, and
government, with the goal of developing a consensus list of Big Data
requirements across all stakeholders. This includes gathering and
understanding various use cases from diversified application domains.
Tasks
•Gather use case input from all stakeholders
•Derive Big Data requirements from each use case.
•Analyze/prioritize a list of challenging general requirements that may delay
or prevent adoption of Big Data deployment
•Work with Reference Architecture to validate requirements and reference
architecture
•Develop a set of general patterns capturing the “essence” of use cases (to
do)

3
Use Case Template
• 26 fields completed for
51 usecases
– Government Operation: 4
– Commercial: 8
– Defense: 3
– Healthcare and Life
Sciences: 10
– Deep Learning and Social
Media: 6
– The Ecosystem for
Research: 4
– Astronomy and Physics: 5
– Earth, Environmental and
Polar Science: 10
– Energy: 1

4
51 Detailed Use Cases: Many TB’s to Many PB’s
• Government Operation: National Archives and Records Administration, Census Bureau
• Commercial: Finance in Cloud, Cloud Backup, Mendeley (Citations), Netflix, Web Search,
Digital Materials, Cargo shipping (as in UPS)
• Defense: Sensors, Image surveillance, Situation Assessment
• Healthcare and Life Sciences: Medical records, Graph and Probabilistic analysis, Pathology,
Bioimaging, Genomics, Epidemiology, People Activity models, Biodiversity
• Deep Learning and Social Media: Driving Car, Geolocate images/cameras, Twitter, Crowd
Sourcing, Network Science, NIST benchmark datasets
• The Ecosystem for Research: Metadata, Collaboration, Language Translation, Light source
experiments
• Astronomy and Physics: Sky Surveys compared to simulation, Large Hadron Collider at
CERN, Belle Accelerator II in Japan
• Earth, Environmental and Polar Science: Radar Scattering in Atmosphere, Earthquake,
Ocean, Earth Observation, Ice sheet Radar scattering, Earth radar mapping, Climate simulation
datasets, Atmospheric turbulence identification, Subsurface Biogeochemistry (microbes to
watersheds), AmeriFlux and FLUXNET gas sensors
• Energy: Smart grid
Next step involves matching extracted requirements and reference architecture.
Alternatively develop a set of general patterns capturing the “essence” of use cases.

5
Some Trends
• Practitioners consider themselves Data Scientists
• Images are a major source of Big Data
– Radar
– Light Synchrotrons
– Phones
– Bioimaging
5
• Hadoop and HDFS dominant
• Business – main emphasis at
NIST – interested in analytics and
assume HDFS
• Academia also extremely
interested in data management
• Clouds v. Grids

6
Example Use Case I: Summary of Genomics
• Application: 19: NIST Genome in a Bottle Consortium
– integrates data from multiple sequencing technologies and methods
– develops highly confident characterization of whole human genomes as
reference materials,
– develops methods to use these Reference Materials to assess performance of
any genome sequencing run.
• Current Approach:
– The storage of ~40TB NFS at NIST is full; there are also PBs of genomics data
at NIH/NCBI.
– Use Open-source sequencing bioinformatics software from academic groups on
a 72 core cluster at NIST supplemented by larger systems at collaborators.
• Futures:
– DNA sequencers can generate ~300GB compressed data/day which volume
has increased much faster than Moore’s Law.
– Future data could include other ‘omics’ measurements, which will be even larger
than DNA sequencing. Clouds have been explored.
Healthcare/Life Sciences

7
Example Use Case II: Census Bureau Statistical
Survey Response Improvement (Adaptive Design)
• Application: Survey costs are increasing as survey response declines.
– Uses advanced “recommendation system techniques” that are open and scientifically objective
– Data mashed up from several sources and historical survey para-data (administrative data about the
survey) to drive operational processes
– The end goal is to increase quality and reduce the cost of field surveys
– ~1PB of data coming from surveys and other government administrative sources.
– Data can be streamed with approximately 150 million records transmitted as field data streamed
continuously, during the decennial census.
– All data must be both confidential and secure.
– All processes must be auditable for security and confidentiality as required by various legal statutes.
– Data quality should be high and statistically checked for accuracy and reliability throughout the
collection process.
– Use Hadoop, Spark, Hive, R, SAS, Mahout, Allegrograph, MySQL, Oracle, Storm, BigMemory,
Cassandra, Pig software.
• Futures:
– Analytics needs to be developed which give statistical estimations that provide more detail, on a more
near real time basis for less cost.
– The reliability of estimated statistics from such “mashed up” sources still must be evaluated.
Government Operation

8
Example Use Case III: 26: Large-scale Deep Learning
• Application: 26: Large-scale Deep Learning
– Large models (e.g., neural networks with more neurons and connections) combined with large datasets
are increasingly the top performers in benchmark tasks for vision, speech, and Natural Language
Processing.
– One needs to train a deep neural network from a large (>>1TB) corpus of data (typically imagery, video,
audio, or text).
– Such training procedures often require customization of the neural network architecture, learning
criteria, and dataset pre-processing.
– In addition to the computational expense demanded by the learning algorithms, the need for rapid
prototyping and ease of development is extremely high.
– The largest applications so far are to image recognition and scientific studies of unsupervised learning
with 10 million images and up to 11 billion parameters on a 64 GPU HPC Infiniband cluster.
– Both supervised (using existing classified images) and unsupervised applications investigated.
• Futures:
– Large datasets of 100TB or more may be necessary in order to exploit the representational power of
the larger models.
– Training a self-driving car could take 100 million images at megapixel resolution.
– Deep Learning shares many characteristics with the broader field of machine learning. The paramount
requirements are high computational throughput for mostly dense linear algebra operations, and
extremely high productivity for researcher exploration.
– One needs integration of high performance libraries with high level (python) prototyping environments.
8
Deep Learning and Social Media

9
Example Use Case IV:
EISCAT 3D incoherent scatter radar system
• Application: EISCAT 3D incoherent scatter radar system
– EISCAT: European Incoherent Scatter Scientific Association
– Research on the lower, middle and upper atmosphere and ionosphere using the incoherent scatter radar
technique.
– This technique is the most powerful ground-based tool for these research applications.
– EISCAT studies instabilities in the ionosphere, as well as investigating the structure and dynamics of the
middle atmosphere. It is also a diagnostic instrument in ionospheric modification experiments with
addition of a separate Heating facility.
– Currently EISCAT operates 3 of the 10 major incoherent radar scattering instruments worldwide with its
facilities in in the Scandinavian sector, north of the Arctic Circle.
– The current old EISCAT radar generates terabytes per year rates and no present special challenges.
• Futures:
– The next generation radar, EISCAT_3D, will consist of a core site with a transmitting and receiving radar
arrays and four sites with receiving antenna arrays at some 100 km from the core.
– The fully operational 5-site system will generate several thousand times data of current EISCAT system
with 40 PB/year in 2022 and is expected to operate for 30 years.
– EISCAT 3D data e-Infrastructure plans to use the high performance computers for central site data
processing and high throughput computers for mirror sites data processing.
– Downloading the full data is not time critical, but operations require real-time information about certain
pre-defined events to be sent from the sites to the operation center and a real-time link from the operation
center to the sites to set the mode of radar operation on with immediate action.
9
Astronomy and Physics

10
• Application: 51: Consumption forecasting in Smart Grids
– Predict energy consumption for customers, transformers, sub-stations and the electrical grid
service area using smart meters providing measurements every 15-mins at the granularity of
individual consumers within the service area of smart power utilities.
– Combine Head-end of smart meters (distributed), Utility databases (Customer Information,
Network topology; centralized), US Census data (distributed), NOAA weather data (distributed),
Micro-grid building information system (centralized), Micro-grid sensor network (distributed).
– This generalizes to real-time data-driven analytics for time series from cyber physical systems
– GIS based visualization.
– Data is around 4 TB a year for a city with 1.4M sensors in Los Angeles.
– Uses R/Matlab, Weka, Hadoop software.
– Significant privacy issues requiring anonymization by aggregation.
– Combine real time and historic data with machine learning for predicting consumption.
• Futures:
– Wide spread deployment of Smart Grids with new analytics integrating diverse data and
supporting curtailment requests. Mobile applications for client interactions.
Energy
Example Use Case V: Consumption forecasting in
Smart Grids

11
• Application: 17:Pathology Imaging/ Digital Pathology II
– 1GB raw image data + 1.5GB analytical results per 2D image.
– MPI for image analysis; MapReduce + Hive with spatial extension on supercomputers and clouds.
– GPU’s used effectively. Figure below shows the architecture of Hadoop-GIS, a spatial data warehousing system over
MapReduce to support spatial analytics for analytical pathology imaging.
Example Use Case VI: Pathology Imaging
Architecture of Hadoop-GIS, a spatial data warehousing system over
MapReduce to support spatial analytics for analytical pathology imaging
• Futures: Recently, 3D pathology
imaging is made possible through 3D
laser technologies or serially
sectioning hundreds of tissue
sections onto slides and scanning
them into digital images. Segmenting
3D microanatomic objects from
registered serial images could
produce tens of millions of 3D objects
from a single image. This provides a
deep “map” of human tissues for next
generation diagnosis. 1TB raw image
data + 1TB analytical results per 3D
image and 1PB data per moderated
hospital per year.

12
• Application: 20: Comparative analysis for metagenomes and genomes
– Given a metagenomic sample, (1) determine the community composition in terms of other
reference isolate genomes, (2) characterize the function of its genes, (3) begin to infer
possible functional pathways, (4) characterize similarity or dissimilarity with other
metagenomic samples, (5) begin to characterize changes in community composition and
function due to changes in environmental pressures, (6) isolate sub-sections of data
based on quality measures and community composition.
– Integrated comparative analysis system for metagenomes and genomes, front ended by an
interactive Web UI with core data, backend precomputations, batch job computation submission
from the UI.
– Provide interface to standard bioinformatics tools (BLAST, HMMER, multiple alignment and
phylogenetic tools, gene callers, sequence feature predictors…).
• Futures:
– Management of heterogeneity of biological data is currently performed by RDMS (Oracle).
Unfortunately, it does not scale for even the current volume 50TB of data.
– NoSQL solutions aim at providing an alternative but unfortunately they do not always lend
themselves to real time interactive use, rapid and parallel bulk loading, and sometimes
have issues regarding robustness.
Example Use Case VII: Metagenomics

13
• Application: 27: Organizing large-scale, unstructured
collections of consumer photos
– Produce 3D reconstructions of scenes using collections of millions to billions of
consumer images, where neither the scene structure nor the camera positions
are known a priori.
– Use resulting 3d models to allow efficient browsing of large-scale photo
collections by geographic position.
– Geolocate new images by matching to 3d models. Perform object recognition on
each image. 3d reconstruction posed as a robust non-linear least squares
optimization problem where observed relations between images are constraints
and unknowns are 6-d camera pose of each image and 3-d position of each
point in the scene.
– Hadoop cluster with 480 cores processing data of initial applications.
– Note over 500 billion images on Facebook and over 5 billion on Flickr with over
500 million images added to social media sites each day.
13
Deep Learning Social Networking
Example Use Case VIII: Consumer photography

14
27: Organizing large-scale, unstructured collections of
consumer photos II
• Futures:
– Need many analytics including feature extraction, feature matching, and large-scale
probabilistic inference, which appear in many or most computer vision and image
processing problems, including recognition, stereo resolution, and image denoising.
– Need to visualize large-scale 3-d reconstructions, and navigate large-scale collections of
images that have been aligned to maps.

15
• Application: 28: Truthy: Information diffusion research from
Twitter Data
– Understanding how communication spreads on socio-technical networks.
– Detecting potentially harmful information spread at the early stage (e.g., deceiving
messages, orchestrated campaigns, untrustworthy information, etc.)
– 1) Acquisition and storage of a large volume (30 TB a year compressed) of continuous
streaming data from Twitter (~100 million messages/day, ~500GB data/day increasing);
– (2) near real-time analysis of such data, for anomaly detection, stream clustering, signal
classification and online-learning;
– 3) data retrieval, big data visualization, data-interactive Web interfaces, public API for data
querying. Use Python/SciPy/NumPy/MPI for data analysis. Information diffusion,
clustering, and dynamic network visualization capabilities already exist
• Futures:
– Truthy plans to expand incorporating Google+ and Facebook.
– Need to move towards Hadoop/IndexedHBase & HDFS distributed storage.
– Use Redis as an in-memory database to be a buffer for real-time analysis.
– Need streaming clustering, anomaly detection and online learning.
15
Example Use Case IX: Twitter Data

16
1
Part of Property Summary Table

17
Requirements Gathering
• Data sources
– data size, file formats, rate of grow, at rest or in motion, etc.
• Data lifecycle management
– curation, conversion, quality check, pre-analytic processing, etc.
• Data transformation
– data fusion/mashup, analytics
• Capability infrastructure
– software tools, platform tools, hardware resources such as storage
and networking
• Security & Privacy; and data usage
– processed results in text, table, visual, and other formats
A total of 437 specific requirements under 35
high-level generalized requirement summaries.

18
Interaction Between Subgroups
Technology
Roadmap
Requirements
& Use Cases
Definitions &
Taxonomies

Reference
Architecture 


Security &
Privacy


Due to time constraints, activities were carried out in parallel.

19
Reference
Architecture
• Multiple stacks of
technologies
– Open and
Proprietary
• Provide example
stacks for different
applications
• Come up with usage
patterns and best
practices

20
Next Steps
• Approach for RDA to implement use cases
and NBD to identify abstract interface
• Planning for implementation of usecases
– Resource availability
– Application-specific support
– Computation and storage leverage
• Multiple potential directions
– Prioritization is one of the goals for this meeting.

21
Key Links
• Use cases listing:
http://bigdatawg.nist.gov/usecases.php
• Latest version of the document (Dated Oct 12,
2013):
http://bigdatawg.nist.gov/_uploadfiles/M0245_
v5_6066621242.docx

big_data_casestudies_2.ppt

Related slideshows

Recommended for you

Recommended for you

Recommended for you

Recommended for you

Recommended for you

More Related Content

What's hot

What's hot (20)

Similar to big_data_casestudies_2.ppt

Similar to big_data_casestudies_2.ppt (20)

More from vishal choudhary

More from vishal choudhary (20)

Recently uploaded

Recently uploaded (20)

big_data_casestudies_2.ppt